gemini_code_exec

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint and openWorldHint. Description adds behavioral context: execution in a sandbox, statelessness, and return of stdout/stderr/results. No contradictions. Could elaborate on sandbox limitations but overall adds value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states core action and environment, second covers outputs and statefulness. No redundant words, front-loaded with essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a code execution tool, description covers inputs, sandbox environment, and outputs. An output schema exists, so return details are not required. Could be enhanced with information on timeouts or available libraries, but the current description is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with descriptions (code, model). The description does not add new information about parameters; it restates 'Execute Python code' which aligns with the code parameter. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the verb 'Execute' and the resource 'Python code' using 'Gemini's built-in code execution sandbox'. Distinguishes from sibling tools like consult_gemini or gemini_search, which are for querying, not code execution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Describes what the tool does and what it returns (stdout, stderr, results). Mentions it is 'Stateless utility', implying isolated executions. However, no explicit comparison or guidance on when to use this versus alternative tools for similar tasks (e.g., consult_gemini).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.